Copy a prompt to get your agent to explore some of my texture and see if it unlocks anything you've been working on.
Agent context should name what is inferred before it routes.
A route is useful.
But a route is not the source.
It is a reading of the source.
So the agent layer should say what it observed.
Then what it inferred.
Then why the route seems useful.
That keeps the note portable without making the interpretation too confident.
sourced Jun 3 2026 · medium confidence · argue it, don't flatten it
Every page here carries a machine-readable layer underneath: the sources, dates, confidence levels, and connections behind what you just read. I call it undertext. If you read with an agent, give it this page's undertext:
https://jared.is/undertext.json?target=/thinking/2026-06-03-agent-context-should-name-what-is-inferred-before-it-routes/